thijsdezoete makes Mike run start-to-finish on your own machine

One command stands up the whole application - no cloud accounts, no API keys, and an option to run the AI models fully offline.

infrastructureintegration

thijsdezoete has packaged this fork so that a single command brings the entire app to life on a laptop, with nothing signed up for in advance. It bundles everything the backend needs into one self-contained bundle:

  • A built-in database, login, and gateway layer, with the setup applied automatically the first time it boots.
  • Self-hosted file storage that stands in for a cloud storage account, swapped in without touching the rest of the app.
  • A local mail catcher that grabs signup and confirmation emails in an on-machine inbox, so account flows work without a real email provider.
  • Local AI models via Ollama, a tool for running language models on your own hardware: they show up under a "Local" heading in every model picker - chat, titles, and tabular review - need no API key, and run offline. A refresh control re-detects newly installed models on the fly.
So what Worth a look for anyone who wants to evaluate Mike without wiring up outside services, or run it where client data never leaves the machine.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from thijsdezoete/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
230ba0ef Add self-hosted Docker stack with local Supabase, storage, email, and Ollama Thijs de Zoete 2026-06-29 ↗ GitHub
commit body
Bring the whole app up with a single `docker compose up` and no external
accounts.

Self-contained stack:
- Embedded Supabase (Postgres + GoTrue auth + PostgREST + an nginx gateway),
  with the schema auto-loaded on first boot and auth emails auto-confirmable.
- RustFS for S3-compatible object storage, replacing Cloudflare R2.
- Mailpit catches auth emails (signup/confirmation) in a local inbox.
- Production-style image builds for the frontend and backend.

Local models via Ollama:
- New provider speaking Ollama's OpenAI-compatible chat API, including the
  agentic tool-call loop and a graceful fallback for models that don't
  support tools.
- Models are detected dynamically (GET /models/ollama) and appear in every
  model picker (chat, title, tabular review) under a "Local" group, with no
  API key required. Any `ollama/<tag>` id is valid by prefix.
- Manual "Refresh" button on the API Keys page re-detects installed models
  and re-checks key status, pushing updates live to the pickers.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-727.md from inside the repo you want the changes in.

⬇ Download capture-thread-727.md